Training in progress, step 26, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33c9333cf17342a936dd855e8dad5631a4ae4640c00965e3cf50339df3c9206e
+oid sha256:143c28c5deae3fb4128f47506e470c142f96fb77b21e23e121b782bd15e36446
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:adb103200eb35720a3b5ce865805540528f0c156f280940dafb1c6929ddd64bb
+oid sha256:1157b2d97ca0af7992441b60506a469b898620f5289367d9f77c1782514f2265
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb0a9ae08a837d696210720a364c40061c9c8b036f36570a99f11fe3b8d70f51
+oid sha256:562360b448a53e7366b8643d15ad250a0f706aaefd28e30d76b7f5f4480c7196
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 8.082214775532027e-05,
+  "epoch": 0.00016164429551064055,
   "eval_steps": 13,
-  "global_step": 13,
+  "global_step": 26,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -30,6 +30,21 @@
       "eval_samples_per_second": 23.695,
       "eval_steps_per_second": 11.848,
       "step": 13
+    },
+    {
+      "epoch": 0.0001243417657774158,
+      "grad_norm": NaN,
+      "learning_rate": 0.0002,
+      "loss": 0.3708,
+      "step": 20
+    },
+    {
+      "epoch": 0.00016164429551064055,
+      "eval_loss": NaN,
+      "eval_runtime": 1430.9366,
+      "eval_samples_per_second": 23.665,
+      "eval_steps_per_second": 11.833,
+      "step": 26
     }
   ],
   "logging_steps": 10,
@@ -49,7 +64,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1399057243176960.0,
+  "total_flos": 3068899759226880.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null